© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9596
    Prev
    Next
    INDEX
    Explanations

    being late

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikli
    0.66
    頡
    0.65
    тения
    0.64
     دار
    0.61
    칵
    0.61
    кти
    0.60
    DataGridView
    0.60
     संके
    0.59
    ို
    0.59
    থাক
    0.57
    POSITIVE LOGITS
     late
    4.69
     Late
    4.16
    Late
    4.05
    late
    3.86
     delayed
    3.10
     tard
    2.83
     delay
    2.82
    遅
    2.82
    늦
    2.77
    delayed
    2.65
    Activations Density 0.139%

    No Known Activations